© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 29177
    Prev
    Next
    INDEX
    Explanations

    instances of the word "answers."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    365
    +0.14
    0.8%
    450
    +0.13
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.01
    365
    +0.13
    0.01
    307
    +0.12
    0.01
    Negative Logits
    nez
    -1.58
     assumption
    -1.48
    matically
    -1.47
    "?"
    -1.44
    án
    -1.42
     abst
    -1.41
     thanked
    -1.39
    omorphisms
    -1.38
     brow
    -1.37
     correctness
    -1.35
    POSITIVE LOGITS
    oplan
    1.95
    cript
    1.85
    estead
    1.85
    ociety
    1.82
    °
    1.62
    ģ
    1.60
    CRIPT
    1.54
    ound
    1.51
    IJ
    1.48
    lop
    1.48
    Activations Density 0.032%

    No Known Activations